996 Analysis

# Library for visualizing the 3d plot. 
library(plotly)

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

I - Introduction

II - Data Preprocessing

Load datasets

dt_issues = read.csv("data/issues_data.csv", header=TRUE)
dt_star = read.csv("data/stargazers.csv", header=TRUE)
dt_user = read.csv("data/users_data.csv", header=TRUE)

Saniety Check

# Inspect the dataset by taking the first 10 rows of each dataset. 
dt_issues %>% head(10)

dt_star %>% head(10)

dt_user %>% head(10)

Data Cleaning & Wrangling

# User dataset cleaning
# Cleaning
dt_user_cld <- dt_user %>% 
    # Join the issues dataset. 
    left_join(dt_issues, by="X_id") %>%
    select(bio, blog, company, created_at.x, followers, following, hireable, location, login, name, public_gists, 
           type, closed_at, updated_at.x, email, organizations_url, public_repos) %>%
    # Drop unused features. 
    # select(-X_id, -avatar_url, -events_url, -followers_url, -following_url, 
    #        -gists_url, -gravatar_id, -html_url, -node_id, -public_gists, -received_events_url, 
    #        -repos_url, -site_admin, -starred_url, -subscriptions_url, -type) %>%
    # Convert the time/date features to relative format. 
    mutate(created_at = lubridate::ymd_hms(created_at.x), 
           updated_at = lubridate::ymd_hms(updated_at.x)) %>%
    # Convert various factor type features to string type. 
    mutate(bio = as.character(bio), 
           blog = as.character(blog), 
           company = as.character(company), 
           email = as.character(email), 
           location = as.character(location), 
           login = as.character(login), 
           name = as.character(name), 
           organizations_url = as.character(organizations_url))

Column `X_id` joining factors with different levels, coercing to character vector

str(dt_user_cld)

'data.frame':   39987 obs. of  19 variables:
 $ bio              : chr  "" "" "" "" ...
 $ blog             : chr  "" "" "" "" ...
 $ company          : chr  "" "" "" "" ...
 $ created_at.x     : Factor w/ 39971 levels "2008-03-26T03:33:42Z",..: 23111 24348 13701 27767 34585 17517 19613 22254 23043 18383 ...
 $ followers        : int  9 4 7 2 0 2 13 5 1 0 ...
 $ following        : int  16 38 14 89 0 0 21 126 48 1 ...
 $ hireable         : Factor w/ 2 levels "","True": 1 1 1 1 1 1 1 1 1 1 ...
 $ location         : chr  "" "" "" "" ...
 $ login            : chr  "moloach" "bhxch" "YueNing" "BigFaceCatMhc" ...
 $ name             : chr  "" "Zhe Lee" "naodongbanana" "" ...
 $ public_gists     : int  0 0 0 0 0 0 1 24 0 0 ...
 $ type             : Factor w/ 1 level "User": 1 1 1 1 1 1 1 1 1 1 ...
 $ closed_at        : logi  NA NA NA NA NA NA ...
 $ updated_at.x     : Factor w/ 38705 levels "2015-10-22T09:47:56Z",..: 14522 14681 25825 31448 31450 37456 23803 31101 4862 19705 ...
 $ email            : chr  "" "mytempbh@outlook.com" "n1085633848@outlook.com" "" ...
 $ organizations_url: chr  "https://api.github.com/users/moloach/orgs" "https://api.github.com/users/bhxch/orgs" "https://api.github.com/users/YueNing/orgs" "https://api.github.com/users/BigFaceCatMhc/orgs" ...
 $ public_repos     : int  10 34 29 4 0 26 93 102 13 2 ...
 $ created_at       : POSIXct, format: "2016-07-12 05:17:50" "2016-08-27 14:04:23" "2015-06-19 13:57:11" "2017-01-14 03:30:31" ...
 $ updated_at       : POSIXct, format: "2019-03-09 00:15:05" "2019-03-09 09:30:45" "2019-03-25 10:50:50" "2019-03-28 00:02:38" ...

# Issues dataset cleaning
dt_issues_cld <- dt_issues %>%
    # Drop unused features. 
    select(created_at, body, comments, created_at, title, user.login) %>%
    # Convert the time/date features to relative format. 
    mutate(created_at = lubridate::ymd_hms(created_at), 
           # Convert the factor type features to the correct format. 
           body = as.character(body), 
           title = as.character(title), 
           user.login = as.character(user.login))

III - Data Analysis

1. Supporters’ Profile Analysis

1. What Companies/Universities are those programmers from?

company_info <- dt_user_cld %>% 
    group_by(company) %>%
    summarise(count = n()) %>%
    arrange(desc(count)) %>%
    filter(company != "")
# Display the top companies. 
company_info

# Define the company aggregation function. 
company_aggregation <- function(name) {
    # Make case insensitive. 
    orig_name <- name
    name <- toupper(name)
    # Detect pattern and change the company name accordingly. 
    if (grepl("百度|BAIDU|AIDU", name)) {
        target_name <- "Baidu"
    } else if (grepl("ENCENT|腾讯|TENCENT", name)) {
        target_name <- "Tencent"
    } else if (grepl("LIBABA|淘宝|AOBAO|LIPAY|阿里巴巴|LIYUN|阿里云", name)) {
        target_name <- "Alibaba"
    } else if (grepl("JD|京东", name)) {
        target_name <- "JD"
    } else if (grepl("ETEASE|网易", name)) {
        target_name <- "NetEase"
    } else if (grepl("EITUAN|美团", name)) {
        target_name <- "MeiTuan"
    } else if (grepl("YTEDANCE|字节|头条", name)) {
        target_name <- "ByteDance"
    } else if (grepl("ELEME|饿了", name)) {
        target_name <- "Eleme"
    } else if (grepl("UAWEI|华为", name)) {
        target_name <- "Huawei"
    } else if (grepl("DIDI|滴滴|嘀嘀", name)) {
        target_name <- "DiDi"
    } else {
        target_name <- orig_name
    }
    
    return (target_name)
}
# Define the education aggregation function. 
education_aggregation <- function(name) {
    # Make case insensitive
    orig_name <- name
    name <- toupper(name)
    # Detect pattern and change the education accordingly. 
    if (grepl("HEJIANG|ZJU|浙江大学|浙大", name)) {
        target_name <- "Zhejiang University"
    } else if (grepl("SINGHUA|清华", name)) {
        target_name <- "Tsinghua University"
    } else if (grepl("SHANGHAI JIAO TONG|SJTU|上海交大|上海交通", name)) {
        target_name <- "Shanghai Jiao Tong University"
    } else if (grepl("UESTC|电子科大|电子科技", name)) {
        target_name <- "University of Electronic Science and Technology of China"
    } else if (grepl("USTC|中科大|中国科学技术", name)) {
        target_name <- "University of Science and Technology of China"
    } else if (grepl("FUDAN|复旦", name)) {
        target_name <- "Fudan University"
    } else if (grepl("ARBIN|哈", name)) {
        target_name <- "Harbin Institute of Technology"
    } else if (grepl("BUPT|北邮|北京邮电", name)) {
        target_name <- "Beijing University of Post and Telecommunications"
    } else {
        target_name <- NA
    }
    
    return (target_name)
}
# Aggregating disparse companies. 
agg_companies <- rep(NA, nrow(company_info))
agg_education <- rep(NA, nrow(company_info))
for (i in 1:nrow(company_info)) {
    agg_companies[i] <- company_aggregation(company_info$company[i])
    agg_education[i] <- education_aggregation(company_info$company[i])
}
company_info_agg <- cbind(company_info, agg_companies, agg_education)

# Show the top ten companies which have the most number of developer support 996.icu
company_info_agg %>% group_by(agg_companies) %>%
    summarise(count = n()) %>%
    arrange(desc(count)) %>% 
    head(10)

# Show what universities are those developers from. 
company_info_agg %>% group_by(agg_education) %>%
    summarise(count = n()) %>%
    arrange(desc(count)) %>%
    filter(!is.na(agg_education)) %>%
    head(10)

Factor `agg_education` contains implicit NA, consider using `forcats::fct_explicit_na`

NA

2. What cities are those developers from?

# 
# Define the function for aggregating the cities. 
city_aggregation <- function(name) {
    # Make case insensitive. 
    orig_name <- name
    name <- toupper(name)
    # Detect pattern and change the education accordingly. 
    if (grepl("EIJING|北京", name)) {
        target_name <- "Beijing"
    } else if (grepl("HANGHAI|上海", name)) {
        target_name <- "Shanghai"
    } else if (grepl("ANGZHOU|杭州", name)) {
        target_name <- "Hangzhou"
    } else if (grepl("UANGZHOU|广州", name)) {
        target_name <- "Hangzhou"
    } else if (grepl("HENGDU|成都", name)) {
        target_name <- "Chengdu"
    } else if (grepl("ANJING|南京", name)) {
        target_name <- "Nanjing"
    } else if (grepl("INGAPORE|新加坡", name)) {
        target_name <- "Singapore"
    } else if (grepl("HONG KONG|香港|HK", name)) {
        target_name <- "Hong Kong"
    } else if (grepl("UHAN|武汉", name)) {
        target_name <- "Wuhan"
    } else {
        target_name <- orig_name
    }
    
    return (target_name)
}
city_info <- dt_user_cld %>% 
    group_by(location) %>%
    summarise(count = n()) %>%
    filter(location != "", 
           location != "China") %>%
    arrange(desc(count))
agg_cities <- rep(NA, nrow(city_info))
for (i in 1:nrow(city_info)) {
    agg_cities[i] <- city_aggregation(city_info$location[i])
} 
city_info_agg <- cbind(city_info, agg_cities)

# Showing the top ten cities that have the most developer support 996.icu
city_info_agg %>% group_by(agg_cities) %>%
    summarise(count = n()) %>%
    filter(agg_cities != "", 
           agg_cities != "China") %>%
    arrange(desc(count)) %>%
    head(10)

3. Summary Statistics of Supporters’ Related Information.

# Summary statistics of supporters' github account. 
dt_user_cld %>% select(followers, following, public_repos) %>%
    gather(stat_type, number, followers, following, public_repos) %>%
#    filter(number <= 10000) %>%
    ggplot(aes(x = factor(stat_type), y = log(number))) +
    geom_jitter(color = "grey", width = .2) +
    geom_boxplot(alpha=0.6) +
    stat_summary(fun.y = "mean", geom = "point", size = 5, color = "red", shape = 15) +
    labs(x = "Summary Statistics of Followers, Following and Public Repos, Mean (red)", 
         y = "Relative Values") +
    ggtitle("Summary Statistics Plot (Log Transformed)")

NA
NA

4. Distribution Plot of Supporters’ Information.

# Distribution graph of supporter's followers under 50. 
dist_ggplot <- dt_user_cld %>% filter(followers <= 50, following <= 50, public_repos <= 50) %>%
    ggplot() +
    geom_bar(aes(x = followers), col="black", fill="black", alpha=0.5) +
    geom_bar(aes(x = following), col="black", fill="red", alpha=0.5) +
    geom_bar(aes(x = public_repos), col="black", fill="blue", alpha=0.5)
    
dist_ggplot + 
    labs(x = "Followers (Black), Following (Red) and Public Repositories (Blue)", 
         y = "Count") +
    ggtitle("Distribution Plot")

5. Distribution Plot of Supporters’ Registration Duration.

# Calculate supporters' number of days since registered the github account. 
today <- lubridate::ymd("2019-04-29")
dt_user_cld <- dt_user_cld %>%
    # Calculate the duration and convert it to numerical value. 
    mutate(duration = as.numeric(as.duration(interval(created_at, today)), "days"))
# Showing average registration years. 
print(mean(dt_user_cld$duration)/365)

[1] 3.321946

# Distribution plot of registration days. 
dt_user_cld %>% ggplot(aes(x = duration/365)) + 
    geom_histogram(col="black", fill="grey", alpha = 0.7) +
    geom_vline(xintercept = mean(dt_user_cld$duration)/365, linetype = "dotted", color = "red", size = 1.5) +
    labs(y = "Frequency / Count", 
         x = "Number of Years Since Registration") +
    ggtitle("Distribution Plot of Supporters' Registration Duration")

2. Statistical Modeling

1. Analyzing the Relationship Between Followers and other factors.

# Select variables for analysis. 
user_stat <- dt_user_cld %>% 
    select(followers, following, public_repos, duration)
# Saniety Check
user_stat %>% head(10)

# Unsupervised Learning: PCA
user_pca <- prcomp(user_stat, center=TRUE, scale.=TRUE)
print(user_pca)

Standard deviations (1, .., p=4):
[1] 1.1689728 0.9810532 0.9575395 0.8684211

Rotation (n x k) = (4 x 4):
                   PC1        PC2         PC3        PC4
followers    0.3419542 -0.8727076  0.30951456  0.1601545
following    0.5162926  0.3258117  0.60978132 -0.5054259
public_repos 0.6008709  0.3352248 -0.09115495  0.7199092
duration     0.5054339 -0.1408987 -0.72391868 -0.4479128

summary(user_pca)

Importance of components:
                          PC1    PC2    PC3    PC4
Standard deviation     1.1690 0.9811 0.9575 0.8684
Proportion of Variance 0.3416 0.2406 0.2292 0.1885
Cumulative Proportion  0.3416 0.5822 0.8115 1.0000

3. Main Questions/Issues of Supporters

1. Trending Issues.

# Showing top ten issues with most comments. 
dt_issues_cld %>% 
    select(title, comments) %>% 
    arrange(desc(comments)) %>%
    head(10)

# Psuedo top ten issues (translated)
psuedo_issues <- data.frame(
    title = c("Discussion Thread", 
              "Any 'Working under 996, sicking in ICU' wallpapers to use?", 
              "Afterwards, I could put 'participated in an open-source project with over 2000+ stars' on my resume", 
              "I don't understant the law, but I'm wondering if there is any legal issue involved?", 
              "Can this repository be in the top-ten stars list on GitHub?", 
              "Substantial suggestions regarding the anti-996 movements.", 
              "It's ugly that the developers taking salaries while complaining about their companies.", 
              "Working overtime tonight, will delete the database when this repo reach over 100k stars", 
              "Cute girl born in 1996 is looking for developer boyfriend now.", 
              "Worship the original post"), 
    comments = c(1243, 62, 53, 39, 37, 30, 30, 26, 25, 24)) %>%
    mutate(title = as.character(title))
psuedo_issues

2. Text Analysis About Topics of 996 Movement.

# Setting the word-split engine
splitter <- worker(stop_word = "data/stopwords.txt")
# Splitting the words. 
seg <- c(splitter[dt_issues_cld$title], splitter[dt_issues_cld$body])
seg <- seg[nchar(seg) > 1]
# Encode the chinese word vector as UTF-8 format. 
Encoding(seg) <- "UTF-8"
# Extract the top 100 
seg_df <- data.frame(seg = seg) %>%
    group_by(seg) %>%
    summarise(freq = n()) %>%
    arrange(desc(freq)) %>%
    head(100)
# Generating word cloud (Chinese Version). 
font_family <- par("family")
par(family = "Adobe Heiti Std R")
wordcloud(words=seg_df$seg, freq=seg_df$freq, 
          colors=brewer.pal(8,"Dark2"), 
          scale=c(4, 0.8))